INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     uphill
    -0.09
    ↓↵↵
    -0.09
    /Table
    -0.09
    /gen
    -0.08
    .TABLE
    -0.08
     normals
    -0.08
    _norm
    -0.08
    .theta
    -0.08
    /colors
    -0.08
    _GEN
    -0.08
    POSITIVE LOGITS
     datas
    0.08
     Egg
    0.08
     конце
    0.07
     Ny
    0.07
    Egg
    0.07
     Hotel
    0.07
     жұм
    0.07
     явля
    0.07
    nit
    0.07
     Nit
    0.07
    Act Density 0.003%

    No Known Activations